基于ICA和小波变换的轴承故障特征提取

Fault Feature Extraction of Bearing Based on ICA and Wavelet Transform

应用独立分量分析方法和小波变换分离轴承的振动信号,提取其状态特征。并对信号进行自相关预处理,突出信号的非高斯成分,较好地满足独立分量分析的前提条件,即源信号统计独立。采用基于负熵的快速独立分量分析(ICA)算法,成功地分离出了信号的一些独立成分。对ICA处理后的分量信号进行小波变换,完成信号检测,消噪,频带分析,以获取故障信号特征,确定故障的位置和强度。研究结果表明,独立分量分析方法和小波变换能提取明显的轴承故障信号特征。

In this paper, the combination of independent component analysis （ICA） and wavelet transform are presented for separating bearing vibration signal and state feature extraction .The preprocessing obviously stands out the nongaussian signals to satisfy the ICA condition, i.e. statistical independence of sources. The fast ICA algorithm based on negentropy separates successfully independent components from the initial vibration signal. The wavelet transform of independent components processed by independent component analysis is used to singular signal inspection , signal-noise separation and signal frequency range analysis , in ordering to identify the fault position and intensity. The research result is shown that independent component analysis and wavelet transform can extracts obvious bearing fault features.